Method and device for controlling a speech dialog system

• US 20070118380A1
• Filed: 06/30/2004
• Published: 05/24/2007
• Est. Priority Date: 06/30/2003
• Status: Abandoned Application

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Konig, Lars
• Application Number:
  US10/562,354
• Publication Number:
  US 20070118380A1
• Time in Patent Office: Days
• US Class Current: 704/270
• CPC Class Codes: B60R 16/0373 Voice control in general G10L
• CPC Class Codes: G01C 21/36 Input/output arrangements for on-board computers
• CPC Class Codes: G01C 21/3608 using speech input, e.g. using speech recognition
• CPC Class Codes: G01C 21/3629 Guidance using speech or audio output, e.g. text-to-speech text to speech systems per se G10L13/00
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

The invention is directed to a method for controlling a speech dialog system comprising the steps of receiving an input signal emanating from a device not being part of the speech dialog system, automatically classifying the input signal according to a predetermined criterion, initiating outputting and output speech signal by the speech dialog system depending on the classification of the input signal.

Claims

1. Method for controlling a speech dialog system, comprising the steps of:

receiving an input signal emanating from a device not being. part of the speech dialog system,

automatically classifying the input signal according to a predetermined criterion,

automatically initiating outputting an output speech signal by the speech dialog system depending on the classification of the input signal.

2. Method according to claim 1, wherein the speech dialog system is inactive when the input signal is received and the initiating step comprises activating the speech dialog system.

3. Method according to claim 1 or 2, further comprising the steps of receiving a speech input signal,

processing the speech input signal by a speech recognition unit, triggering a device not being part of the speech dialog, system or outputting an output speech signal by the speech dialog system depending on the processed speech input signal.

4. Method according to one of the preceding claims, wherein the classifying step comprises classifying according to the device the input signal emanated from and/or according to the priority of the input signal.

5. Method according to one of the preceding claims, wherein the initiating step is preceded by deciding according to a further predetermined criterion at what time outputting the output speech signal is to be initiated.

6. Method according to claim 5, wherein the deciding step comprises deciding that the output speech signal is to be output immediately if the input signal was classified according to a priority above a predetermined threshold.

7. Method according to one claim 5 or 6, wherein the deciding step comprises deciding which output speech signal to output first if two input signals are received within a predetermined time interval.

8. Method according to one of the preceding claims, wherein the device not being part of the navigation system is a mobile phone, an internet browser, a car radio, an email browser, and/or a navigation system.

9. Computer program product directly loadable into an internal memory of a digital computer, comprising software code portions for performing the steps of the method according to one of the claims 1 to 8.

10. Computer program product stored on a medium readable by a computer system, comprising computer readable program means for causing a computer to perform the steps of the method according to one of the claims 1 to 8.

11. Device for controlling a speech dialog system, in particular, according to the method according to one of the claims 1-7, comprising:

input means for receiving an input signal emanating from a device not being part of the speech dialog system,

classifying means for automatically classifying the input signal according to a predetermined criterion,

initiating means for initiating outputting an output speech signal by the speech dialog system depending on the classification of the input signal.

12. Device according to claim 11 wherein the initiating means is configured to activate the speech dialog system if the speech dialog system is inactive.

13. Device according to claim 11 or 12, wherein the classifying means is configured to classify according to the device the input signal emanated from and/or according to the priority of the input signal.

14. Device according to one of the claims 11-13, further comprising deciding means to decide according to a further predetermined criterion at what time out-putting the output speech signal is to be initiated.

15. Device according to one of the claims 11-14, the device being configured to be activated and/or deactivated via a speech command.

16. Device according to one of the claims 11-15, wherein input means is configured to receive an input signal from a mobile phone, an internet browser, a car radio, an email browser, and/or a navigation system.

17. Vehicle comprising a device according to one of the claims 11-16.